ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Appearance and Motion based Deep Learning Architecture for Moving Object Detection in Moving Camera
Cited 9 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
저자
허병호, 윤기민, 최진영
발행일
201709
출처
International Conference on Image Processing (ICIP) 2017, pp.1827-1831
DOI
https://dx.doi.org/10.1109/ICIP.2017.8296597
협약과제
17HS3600, (1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 박종열
초록
Background subtraction from the given image is a widely used method for moving object detection. However, this method is vulnerable to dynamic background in a moving camera video. In this paper, we propose a novel moving object detection approach using deep learning to achieve a robust performance even in a dynamic background. The proposed approach considers appearance features as well as motion features. To this end, we design a deep learning architecture composed of two networks: an appearance network and a motion network. The two networks are combined to detect moving object robustly to the background motion by utilizing the appearance of the target object in addition to the motion difference. In the experiment, it is shown that the proposed method achieves 50 fps speed in GPU and outperforms state-of-the-art methods for various moving camera videos.
키워드
Deep learning, Moving camera, Moving object detection
KSP 제안 키워드
Appearance features, Background subtraction(BS), Dynamic background, Moving Object Detection, Moving camera videos, Robust performance, deep learning(DL), motion features, state-of-The-Art, target object